用cuda进行一维数组的矢量求和

#include <cstdio>


#define N 20

__global__ void (int *a, int *b, int *c){
    int tid = blockIdx.x;
    if(tid< N){
	c[tid] = a[tid] + b[tid];
    }
}


int main(){

    int a[N];
    int b[N];
    int c[N];
    int *dev_a, *dev_b, *dev_c;

    /*cudaMalloc((void**)&dev_a, N*sizeof(int));*/
    /*cudaMalloc((void**)&dev_b, N*sizeof(int));*/
    /*cudaMalloc((void**)&dev_c, N*sizeof(int));*/

    cudaMalloc(&dev_a, N*sizeof(int));
    cudaMalloc(&dev_b, N*sizeof(int));
    cudaMalloc(&dev_c, N*sizeof(int));

    for(int i =0 ; i<N; i++){
	a[i] = i;
	b[i] = i;
    }

    cudaMemcpy(dev_a, a, N*sizeof(int), cudaMemcpyHostToDevice);
    cudaMemcpy(dev_b, b, N*sizeof(int), cudaMemcpyHostToDevice);

    add<<<N,1>>>(dev_a,dev_b,dev_c);

    cudaMemcpy(c, dev_c, N*sizeof(int), cudaMemcpyDeviceToHost);

    cudaFree(dev_a);
    cudaFree(dev_b);
    cudaFree(dev_c);

    for(int i =0 ;i<N; i++){
      //如果错误的访问量dev_c[i]，会报告段错误
	std::cout<<c[i]<<std::endl;
    }
    return 0;

}